Agent Team Kit

Framework enabling AI agent teams to self-manage work queues, clear roles, continuous discovery, and proactive operation via a heartbeat process.

Security Scan

This is an instruction-only process/templating kit for running autonomous agent teams; it does not request credentials or install software and is internally coherent for that purpose, though there are minor documentation inconsistencies and it assumes your agent runtime can spawn sub-agents and modify workspace files.

Purpose & Capability

The files and SKILL.md are a team/process template (INTAKE, ROLES, BACKLOG, HEARTBEAT, etc.). Everything requested (copying templates, editing role files, adding heartbeat checks) aligns with the stated goal of running a self-sustaining agent team. There are no unexpected credential or binary requirements.

Instruction Scope

Instructions direct the agent to read and write workspace files (process/*, HEARTBEAT.md, memory/YYYY-MM-DD.md, STATUS.md) and to spawn sub-agents when certain conditions are met. That behavior fits the kit's purpose but assumes the runtime has permission to modify repository/workspace files and to spawn agents. There are a few minor inconsistencies in the docs (e.g., HEARTBEAT.md references tasks/QUEUE.md which is not part of the template; README suggests cloning from a reflectt URL while package.json repo differs) that should be resolved before use.

Install Mechanism

No install spec or external downloads — this is instruction-only. Nothing is written to disk by an installer; the only file operations are those the instructions ask users/agents to perform in the workspace.

Credentials

The skill declares no required environment variables or credentials. It does reference models and memory patterns in auxiliary docs (agents-config-draft mentions anthropic models), but those are advisory — not required env variables. There is no unexplained request for secrets.

Persistence & Privilege

The skill is not force-included (always: false) and does not attempt to modify other skills or system-wide configs. It instructs agents to update local workspace files and memory logs, which is normal for a process/template skill. It does assume autonomous invocation/spawning capability, which is expected but should be considered by the user.

Assessment

This kit is broadly coherent and useful if you want autonomous agents maintaining a self-service backlog, but review a few things before installing: - Source & provenance: The package has no description/homepage and the README references a different repo than package.json; confirm you trust the source and intended repository before copying files into your workspace. - File-write & spawn assumptions: The instructions assume the agent runtime can read/write workspace files and spawn sub-agents. If you run agents in a restricted environment, verify those capabilities and permissions first. - Missing/incorrect references: HEARTBEAT.md mentions tasks/QUEUE.md (not present in the template); check for typos or adjust the heartbeat checks to match your repo layout (process/BACKLOG.md is the canonical queue here). - Data sensitivity: Heartbeat and memory log recommendations (memory/YYYY-MM-DD.md, STATUS.md) will record activity; ensure you’re not inadvertently logging secrets or private data into project files that might be backed up or shared. - Control autonomy: The kit promotes autonomous spawning and self-service pickup of tasks. If you want tighter human oversight, adapt the rules (e.g., require human approval for certain priority tasks, or disable autonomous spawning in your runtime). - Backup and test: Copy templates into a disposable workspace first and test behavior; do not run on critical repos without auditing. If you want, I can: (a) list the exact file edits the SKILL.md would have an agent perform, (b) produce a short checklist to harden the heartbeat (e.g., rate limiting spawns, requiring approvals for high-priority tasks), or (c) check the repo URL inconsistencies and propose corrected text for README/HEARTBEAT.md.

Agent Team Kit — SKILL.md

A framework for self-sustaining AI agent teams.

---

What This Is

A complete team process kit for OpenClaw agents that enables:

• Self-service work queues — Agents pick up tasks without human bottlenecks
• Clear role ownership — Everyone knows who does what
• Continuous discovery — Work flows in automatically
• Proactive operation — The team runs itself via heartbeat

---

Quick Start

1. Copy the Process Files

# From your workspace root
cp -r skills/agent-team-kit/templates/process ./process

This creates:

• process/INTAKE.md — The 5-phase work loop
• process/ROLES.md — Role definitions
• process/OPPORTUNITIES.md — Raw ideas/discoveries
• process/BACKLOG.md — Triaged work queue
• process/STATUS.md — Who's working on what

2. Add Heartbeat Config

Merge templates/HEARTBEAT.md into your existing HEARTBEAT.md:

cat skills/agent-team-kit/templates/HEARTBEAT.md >> HEARTBEAT.md

Or copy it directly if you don't have one yet.

3. Customize Roles

Edit process/ROLES.md to match your team:

• Rename roles to fit your domain
• Add/remove specialized execution roles
• Update the human lead section with your name

---

The Intake Loop

DISCOVER → TRIAGE → READY → EXECUTE → FEEDBACK
    ↑                                      ↓
    └──────────────────────────────────────┘

1. Discover — Find opportunities (Scout role)
2. Triage — Decide what's ready (Rhythm role)
3. Ready — Self-service queue (any agent)
4. Execute — Do the work (assigned agent)
5. Feedback — Learn and spawn new ideas (completing agent)

---

Core Roles

Role	Mission	Owns
Scout 🔍	Find opportunities	OPPORTUNITIES.md, discovery
Rhythm 🥁	Keep work flowing	BACKLOG.md, triage
Harmony 🤝	Keep team healthy	Unblocking, retros
[Human]	Strategic direction	Hard calls, spawning

Execution roles (spawn as needed):

• Link 🔗 — Builder
• Pixel 🎨 — Designer
• Sage 🦉 — Architect
• Echo 📢 — Voice
• Spark ✨ — Creative

---

Key Principles

Self-Service

If it's in Ready, any agent can pick it up. No approval needed.

Clear Ownership

Every phase has ONE owner. No ambiguity.

Always Log

Ideas, discoveries, completions — if you don't log it, it didn't happen.

Spawn, Don't Solo

Main agent coordinates. Sub-agents execute. Don't do everything yourself.

---

File Structure

process/
├── INTAKE.md         # How the loop works (reference)
├── ROLES.md          # Who does what
├── OPPORTUNITIES.md  # Raw discoveries (anyone adds)
├── BACKLOG.md        # Triaged work (Rhythm maintains)
└── STATUS.md         # Current activity (self-updated)

HEARTBEAT.md          # Proactive check triggers

---

Heartbeat Integration

Add to your heartbeat checks:

### Team Health (run hourly)
- [ ] OPPORTUNITIES.md stale? → Spawn Scout
- [ ] Ready queue empty? → Alert Rhythm  
- [ ] Active work stuck >2h? → Nudge owner
- [ ] Any unresolved blockers? → Harmony

The heartbeat keeps the loop spinning even when the human isn't watching.

---

Customization

Adding a New Role

1. Define in ROLES.md:

   • Mission (one sentence)
   • Owns (what they're responsible for)
   • Cadence (how often they work)
   • Outputs (what they produce)

2. Update the ownership matrix

3. Add spawn criteria in INTAKE.md if needed

Changing the Loop

The 5-phase loop is flexible. Adapt it:

• Add validation gates between phases
• Split EXECUTE into parallel tracks
• Add approval checkpoints (if your domain requires it)

---

Anti-Patterns

❌ Human manually adds every task → Use triage role instead
❌ Waiting for permission to pick up work → Ready = fair game
❌ One agent does everything → Spawn specialists
❌ Ideas stay in heads → Log to OPPORTUNITIES.md
❌ Heartbeat just returns OK → Actually check the loop

---

Metrics (Optional)

Track team health:

• Cycle time — OPPORTUNITIES → DONE
• Queue depth — Items in Ready (healthy: 5-15)
• Stale items — Days since last triage
• Spawn rate — Sub-agents created per day

---

The system runs itself. Your job is to trust it.